一种基于注意力模型的带钢表面缺陷识别算法  

Recognition Algorithm of Strip Steel Surface Defects Based on Attention Model

作　　者：陆雅诺 陈炳才 陈德刚[1] 闫世祥 李顺平 Lu Yanuo;Chen Bingcai;Chen Degang;Yan Shixiang;Li Shunping(School of Computer Science and Technology,Xinjiang Normal University,Urumqi,Xinjiang 830054,China;College of Computer Science and Technology,Dalian University of Technology,Dalian,Liaoning 116024,China)

机构地区：[1]新疆师范大学计算机科学技术学院,新疆乌鲁木齐830054 [2]大连理工大学计算机科学与技术学院,辽宁大连116024

出　　处：《激光与光电子学进展》2021年第14期234-242,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61961040,61771089);新疆维吾尔自治区“天山青年计划”(2018Q024);自治区区域协同创新专项(科技援疆计划)(2020E0247,2019E0214)。

摘　　要：为了提高工业带钢的质量和产量,针对传统人工识别难度大、效率低和客观性不够等问题,提出了一种基于软注意力机制的带钢表面缺陷识别方法,对传统深度残差网络ResNet模型进行了改进,使用伪彩色图像增强技术处理图片,得到了新的训练集。实验结果表明,在不同信噪比情况下,相比于传统的模型,改进模型A-ResNet50和A-ResNet101都能准确识别不同类型的带钢表面缺陷图像,在测试集上的准确率分别为98.61%和98.05%,单位推断时间达到了0.078 s和0.130 s,证实了A-ResNet50和A-ResNet101模型在带钢表面缺陷识别上的可行性以及可靠性。所提出的方法识别精度高,实现了带钢表面缺陷的智能识别,同时满足工业识别需求。In order to improve the quality and output of industrial strip steels and address the problems of traditional manual identification such as identification difficulty,low efficiency and lack of objectivity,we propose a method for identifying strip steel surface defects based on the soft attention mechanism and improve the traditional deep residual network ResNet model.Moreover,we use the pseudo-color image enhancement technique to process images and obtain new training sets.The experimental results show that compared with the traditional models,the improved models of A-ResNet50 and A-ResNet101 can both accurately identify different types of strip steel surface defect images under different signal-to-noise ratios.The accuracies on the test set are 98.61%and 98.05%,and the unit inference time is 0.078 sand 0.130 s,respectively.Thus the feasibility and reliability of these two models in the identification of surface defects on strip steels are confirmed.The proposed method possesses a high identification accuracy,which can be used to realize the intelligent identification of surface defects on strip steels and meet the demands of industrial identification.

关 键 词：图像处理 注意力机制 伪彩色图像 深度残差网络 缺陷识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]